Citation

Hashim, Nik Mohd Zarifie and Sulistito, Mahmud Dwi and Azhar, Nur Syahmina Ahmad and Razali, Norazrai Daniel Afiq and Mohd Sam, Mohd Fazli and Abd Rahman, Noor Ziela and Ibrahim, Masrullizam Mat (2026) Energy-Efficient Image Compression for Business Intelligence: Comparative Insights on Wavelet-Based Methods. In: Leveraging AI and Big Data for Business Innovation. Springer Science and Business Media Deutschland GmbH, pp. 531-541. ISBN 978-3-032-20412-7

Text Energy-Efficient Image Compression for Business Intelligence_ Comparative Insights on Wavelet-Based Methods _ Springer Nature Link.pdf - Published Version Restricted to Repository staff only Download (671kB)

Abstract

In an era defined by data driven decision systems, sustainable innovation in digital imaging plays a pivotal role in enhancing business operations and reducing computational overhead. This paper presents a comparative study of lightweight wavelet-based image compression techniques, namely Multiresolution (MR) and Direct Product (DP), using both Haar and Daubechies filters, benchmarked against the industry standard JPEG2000 format. The evaluation, conducted across 13 diverse grayscale images, employed five key quantitative metrics which are Peak Signal to Noise Ratio (PSNR), Structural Similarity Index (SSIM), Mean Squared Error (MSE), Normalized Root Mean Squared Error (NRMSE), and Entropy. Experimental results demonstrate that JPEG2000 yields near perfect fidelity with SSIM close to 1.000 and MSE approaching zero. Among wavelet-based methods, Direct Product with Haar wavelets achieves the highest average PSNR of 38.12 decibels and strong SSIM of 0.964, while Multiresolution with Daubechies filters consistently maintains structural integrity with an average SSIM of 0.970 and the lowest variance in PSNR and NRMSE. Furthermore, entropy values across methods remain high, indicating good preservation of image information essential for post compression analytics. These findings establish wavelet-based compression as a viable and energy efficient alternative to conventional formats, aligning with modern business objectives for green IT, cloud optimization, and real time image analytics. The study supports the integration of adaptive transform coding in business infrastructures committed to sustainable digital transformation, providing a practical roadmap for low cost and high-quality visual data management in intelligent systems

Item Type:	Book Section
Uncontrolled Keywords:	Energy-efficient image processing
Subjects:	T Technology > TA Engineering (General). Civil engineering (General) > TA1501-1820 Applied optics. Photonics
Divisions:	Faculty of Engineering and Technology (FET)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	28 Oct 2026 09:05
Last Modified:	28 Oct 2026 09:05
URII:	http://shdl.mmu.edu.my/id/eprint/16962

Downloads

Edit (login required)